清理中间过程脚本和程序文件，保留与Nomad v1.10.5一致的核心配置文件

scripts/utilities/fix-master-binary.sh

@@ -1,26 +0,0 @@
-#!/bin/bash
-
-echo "🔧 使用 HashiCorp 官方脚本修复 master 节点二进制文件..."
-
-# 停止 nomad 服务
-echo '3131' | sudo -S systemctl stop nomad || true
-echo '3131' | sudo -S pkill -9 -f nomad || true
-
-# 删除旧的二进制文件
-echo '3131' | sudo -S rm -f /usr/local/bin/nomad /usr/bin/nomad
-
-# 使用 HashiCorp 官方安装脚本（自动检测架构）
-curl -fsSL https://apt.releases.hashicorp.com/gpg | sudo apt-key add -
-echo '3131' | sudo -S apt-add-repository "deb [arch=$(dpkg --print-architecture)] https://apt.releases.hashicorp.com $(lsb_release -cs) main"
-echo '3131' | sudo -S apt-get update
-echo '3131' | sudo -S apt-get install -y nomad=1.10.5-1
-
-# 验证安装
-nomad version
-
-# 重启服务
-echo '3131' | sudo -S systemctl daemon-reload
-echo '3131' | sudo -S systemctl enable nomad
-echo '3131' | sudo -S systemctl start nomad
-
-echo "✅ Master 节点二进制文件修复完成！"

scripts/utilities/nomad-diagnosis.sh

@@ -1,124 +0,0 @@
-#!/bin/bash
-
-# 🔍 Nomad 集群快速诊断脚本
-
-echo "🔍 Nomad 集群快速诊断"
-echo "===================="
-echo ""
-
-# 定义节点信息
-declare -A NODES=(
-    ["semaphore"]="local"
-    ["master"]="100.117.106.136:60022"
-    ["ash3c"]="100.116.80.94:22"
-)
-
-declare -A TAILSCALE_IPS=(
-    ["semaphore"]="100.116.158.95"
-    ["master"]="100.117.106.136"
-    ["ash3c"]="100.116.80.94"
-)
-
-echo "📊 1. 本地 Nomad 服务状态"
-echo "------------------------"
-systemctl status nomad --no-pager | head -10 || echo "❌ 本地 Nomad 服务异常"
-echo ""
-
-echo "📊 2. 集群成员状态"
-echo "----------------"
-nomad server members 2>/dev/null || echo "❌ 无法获取集群成员状态"
-echo ""
-
-echo "📊 3. 节点状态"
-echo "------------"
-nomad node status 2>/dev/null || echo "❌ 无法获取节点状态"
-echo ""
-
-echo "🌐 4. 网络连通性测试"
-echo "------------------"
-for node in "${!NODES[@]}"; do
-    ip="${TAILSCALE_IPS[$node]}"
-    echo "测试 $node ($ip):"
-    
-    if [[ "$node" == "semaphore" ]]; then
-        echo "  ✅ 本地节点"
-    else
-        # Ping 测试
-        if ping -c 1 -W 3 "$ip" >/dev/null 2>&1; then
-            echo "  ✅ Ping: 成功"
-        else
-            echo "  ❌ Ping: 失败"
-        fi
-        
-        # 端口测试
-        if timeout 5 bash -c "</dev/tcp/$ip/4647" 2>/dev/null; then
-            echo "  ✅ RPC端口(4647): 开放"
-        else
-            echo "  ❌ RPC端口(4647): 关闭"
-        fi
-        
-        if timeout 5 bash -c "</dev/tcp/$ip/4646" 2>/dev/null; then
-            echo "  ✅ HTTP端口(4646): 开放"
-        else
-            echo "  ❌ HTTP端口(4646): 关闭"
-        fi
-    fi
-    echo ""
-done
-
-echo "🔧 5. 远程节点服务状态"
-echo "-------------------"
-for node in "${!NODES[@]}"; do
-    if [[ "$node" == "semaphore" ]]; then
-        continue
-    fi
-    
-    connection="${NODES[$node]}"
-    ip=$(echo "$connection" | cut -d: -f1)
-    port=$(echo "$connection" | cut -d: -f2)
-    
-    echo "检查 $node ($ip:$port):"
-    
-    if ssh -p "$port" -i ~/.ssh/id_ed25519 -o ConnectTimeout=10 -o StrictHostKeyChecking=no ben@"$ip" "echo '3131' | sudo -S systemctl is-active nomad" 2>/dev/null; then
-        status=$(ssh -p "$port" -i ~/.ssh/id_ed25519 -o ConnectTimeout=10 -o StrictHostKeyChecking=no ben@"$ip" "echo '3131' | sudo -S systemctl is-active nomad" 2>/dev/null)
-        echo "  服务状态: $status"
-        
-        # 检查配置文件中的 bind_addr
-        bind_addr=$(ssh -p "$port" -i ~/.ssh/id_ed25519 -o ConnectTimeout=10 -o StrictHostKeyChecking=no ben@"$ip" "echo '3131' | sudo -S grep 'bind_addr' /etc/nomad.d/nomad.hcl 2>/dev/null" | head -1)
-        echo "  配置绑定地址: $bind_addr"
-        
-        # 检查实际监听端口
-        listening=$(ssh -p "$port" -i ~/.ssh/id_ed25519 -o ConnectTimeout=10 -o StrictHostKeyChecking=no ben@"$ip" "echo '3131' | sudo -S netstat -tlnp | grep :464" 2>/dev/null | head -3)
-        if [[ -n "$listening" ]]; then
-            echo "  监听端口:"
-            echo "$listening" | sed 's/^/    /'
-        else
-            echo "  ❌ 未发现 Nomad 监听端口"
-        fi
-    else
-        echo "  ❌ 无法连接或服务未运行"
-    fi
-    echo ""
-done
-
-echo "📋 6. 问题总结和建议"
-echo "=================="
-
-# 检查是否有 leader
-if nomad server members 2>/dev/null | grep -q "leader"; then
-    echo "✅ 集群有 leader"
-else
-    echo "❌ 集群没有 leader - 这是主要问题！"
-    echo ""
-    echo "🔧 建议的修复步骤："
-    echo "1. 先尝试 ash3c IP 修复: ./scripts/utilities/fix-ash3c-ip.sh"
-    echo "2. 如果还不行，使用核弹级重置: ./scripts/utilities/nuclear-reset.sh"
-    echo "3. 检查 master 节点是否需要重启"
-fi
-
-echo ""
-echo "🔗 有用的链接："
-echo "  Web UI: http://100.116.158.95:4646"
-echo "  日志查看: journalctl -u nomad -f"
-echo ""
-echo "🔍 诊断完成！"

scripts/utilities/nuclear-reset.sh

@@ -1,76 +0,0 @@
-#!/bin/bash
-
-# ☢️ 核弹级 Nomad 重置执行脚本 ☢️
-
-set -e
-
-echo "☢️☢️☢️ 核弹级 Nomad 集群重置 ☢️☢️☢️"
-echo ""
-echo "这个脚本将："
-echo "1. 完全摧毁所有 Nomad 进程和数据"
-echo "2. 重新下载并安装 Nomad 二进制文件"
-echo "3. 创建全新的配置文件"
-echo "4. 重新启动整个集群"
-echo ""
-echo "⚠️  警告：这是不可逆的操作！⚠️"
-echo ""
-
-# 检查是否在正确的目录
-if [[ ! -f "scripts/utilities/NUCLEAR-NOMAD-RESET.yml" ]]; then
-    echo "❌ 错误：请在 /root/mgmt 目录下运行此脚本"
-    exit 1
-fi
-
-# 确认操作
-read -p "你确定要进行核弹级重置吗？输入 'NUCLEAR' 确认: " confirm
-if [[ "$confirm" != "NUCLEAR" ]]; then
-    echo "❌ 操作已取消"
-    exit 1
-fi
-
-echo ""
-echo "🚀 开始核弹级重置..."
-echo ""
-
-# 设置 Ansible 配置
-export ANSIBLE_HOST_KEY_CHECKING=False
-export ANSIBLE_STDOUT_CALLBACK=yaml
-
-# 执行核弹级重置
-echo "📡 执行 Ansible playbook..."
-cd /root/mgmt/configuration
-
-ansible-playbook \
-    -i inventories/production/nomad-cluster.ini \
-    ../scripts/utilities/NUCLEAR-NOMAD-RESET.yml \
-    --extra-vars "ansible_ssh_common_args='-o StrictHostKeyChecking=no'" \
-    -v
-
-echo ""
-echo "⏰ 等待集群稳定..."
-sleep 30
-
-echo ""
-echo "🔍 检查集群状态..."
-
-# 检查集群成员
-echo "📊 集群成员状态："
-nomad server members || echo "❌ 无法获取集群成员状态"
-
-echo ""
-echo "📊 节点状态："
-nomad node status || echo "❌ 无法获取节点状态"
-
-echo ""
-echo "🎯 如果上面显示错误，请等待几分钟后再次检查"
-echo "集群可能需要一些时间来完全启动和同步"
-
-echo ""
-echo "🔧 有用的命令："
-echo "  检查集群成员: nomad server members"
-echo "  检查节点状态: nomad node status"
-echo "  查看日志: journalctl -u nomad -f"
-echo "  Web UI: http://100.116.158.95:4646"
-
-echo ""
-echo "☢️ 核弹级重置完成！☢️"

scripts/utilities/ultimate-nomad-fix.yml

@@ -1,113 +0,0 @@
----
-- name: Ultimate Nomad Cluster Fix - Complete Reset
-  hosts: nomad_cluster
-  become: yes
-  gather_facts: yes
-  vars:
-    nomad_encrypt_key: "NVOMDvXblgWfhtzFzOUIHnKEOrbXOkPrkIPbRGGf1YQ="
-
-  tasks:
-    - name: Stop and disable nomad service completely
-      systemd:
-        name: nomad
-        state: stopped
-        enabled: no
-        daemon_reload: yes
-      ignore_errors: yes
-
-    - name: Kill any remaining nomad processes
-      shell: pkill -f nomad || true
-      ignore_errors: yes
-
-    - name: Remove all nomad data and state
-      file:
-        path: "{{ item }}"
-        state: absent
-      loop:
-        - /opt/nomad/data
-        - /etc/nomad.d/nomad.hcl
-        - /var/log/nomad
-
-    - name: Create clean nomad directories
-      file:
-        path: "{{ item }}"
-        state: directory
-        owner: nomad
-        group: nomad
-        mode: '0755'
-      loop:
-        - /etc/nomad.d
-        - /opt/nomad
-        - /opt/nomad/data
-        - /opt/nomad/alloc_mounts
-        - /var/log/nomad
-
-    - name: Create minimal nomad configuration
-      copy:
-        content: |
-          datacenter = "dc1"
-          region     = "global"
-          data_dir   = "/opt/nomad/data"
-
-          bind_addr = "{{ ansible_default_ipv4.address }}"
-
-          server {
-            enabled          = true
-            bootstrap_expect = 1
-            encrypt          = "{{ nomad_encrypt_key }}"
-          }
-
-          client {
-            enabled = true
-            alloc_dir = "/opt/nomad/alloc_mounts"
-          }
-
-          ui {
-            enabled = true
-          }
-
-          addresses {
-            http = "0.0.0.0"
-            rpc  = "{{ ansible_default_ipv4.address }}"
-            serf = "{{ ansible_default_ipv4.address }}"
-          }
-
-          ports {
-            http = 4646
-            rpc  = 4647
-            serf = 4648
-          }
-
-          log_level = "INFO"
-          log_file  = "/var/log/nomad/nomad.log"
-        dest: /etc/nomad.d/nomad.hcl
-        owner: nomad
-        group: nomad
-        mode: '0640'
-
-    - name: Enable and start nomad service
-      systemd:
-        name: nomad
-        state: started
-        enabled: yes
-        daemon_reload: yes
-
-    - name: Wait for nomad to start
-      wait_for:
-        port: 4646
-        host: "{{ ansible_default_ipv4.address }}"
-        delay: 10
-        timeout: 60
-
-    - name: Check nomad status
-      uri:
-        url: "http://{{ ansible_default_ipv4.address }}:4646/v1/status/leader"
-        method: GET
-      register: nomad_leader
-      retries: 5
-      delay: 5
-      ignore_errors: yes
-
-    - name: Display nomad status
-      debug:
-        msg: "Nomad leader status: {{ nomad_leader.json if nomad_leader.json is defined else 'No leader elected yet' }}"

scripts/utilities/verify-podman-migration.sh

@@ -1,31 +0,0 @@
-#!/bin/bash
-
-echo "=== Nomad Podman Migration Verification ==="
-echo
-
-# Check Nomad service status
-echo "1. Checking Nomad service status..."
-ssh ben@100.84.197.26 "sudo systemctl status nomad --no-pager -l"
-echo
-
-# Check Nomad configuration
-echo "2. Checking Nomad configuration..."
-ssh ben@100.84.197.26 "sudo cat /etc/nomad.d/nomad.hcl | grep -A 10 -B 2 podman"
-echo
-
-# Check Podman socket
-echo "3. Checking Podman socket..."
-ssh ben@100.84.197.26 "ls -la /run/user/*/podman/podman.sock 2>/dev/null || echo 'Podman socket not found'"
-echo
-
-# Check Nomad node status
-echo "4. Checking Nomad node status..."
-ssh ben@100.84.197.26 "sudo -u nomad /usr/local/bin/nomad node status -self | grep -A 10 'Driver Status'" 2>/dev/null || echo "Could not get node status"
-echo
-
-# Test Podman functionality
-echo "5. Testing Podman as nomad user..."
-ssh ben@100.84.197.26 "sudo -u nomad podman version --format '{{.Version}}'" 2>/dev/null || echo "Podman test failed"
-echo
-
-echo "=== Verification Complete ==="